LongLLaVA-9B / tokenizer_config.json
Xidong's picture
Upload tokenizer_config.json with huggingface_hub
21e07de verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|unk|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": true,
"model_max_length": 176000,
"pad_token": "<|pad|>",
"padding_side": "right",
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<|unk|>",
"use_default_system_prompt": false
}